{
  "best_metric": 0.27312836050987244,
  "best_model_checkpoint": "vit_epochs1_batch32_lr5e-05_size224_tiles10_seed1_q3_dropout_v2_test11\\checkpoint-469",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 469,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010660980810234541,
      "grad_norm": 2.002079963684082,
      "learning_rate": 4.9466950959488276e-05,
      "loss": 0.3909,
      "step": 5
    },
    {
      "epoch": 0.021321961620469083,
      "grad_norm": 0.9621203541755676,
      "learning_rate": 4.893390191897655e-05,
      "loss": 0.1535,
      "step": 10
    },
    {
      "epoch": 0.031982942430703626,
      "grad_norm": 0.5087786912918091,
      "learning_rate": 4.840085287846482e-05,
      "loss": 0.0848,
      "step": 15
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 0.3503257632255554,
      "learning_rate": 4.78678038379531e-05,
      "loss": 0.0567,
      "step": 20
    },
    {
      "epoch": 0.053304904051172705,
      "grad_norm": 0.2416423112154007,
      "learning_rate": 4.7334754797441364e-05,
      "loss": 0.0344,
      "step": 25
    },
    {
      "epoch": 0.06396588486140725,
      "grad_norm": 0.3675519824028015,
      "learning_rate": 4.6801705756929645e-05,
      "loss": 0.0263,
      "step": 30
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 0.17501111328601837,
      "learning_rate": 4.626865671641791e-05,
      "loss": 0.0262,
      "step": 35
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 1.7560172080993652,
      "learning_rate": 4.5735607675906185e-05,
      "loss": 0.0274,
      "step": 40
    },
    {
      "epoch": 0.09594882729211088,
      "grad_norm": 0.12559843063354492,
      "learning_rate": 4.520255863539446e-05,
      "loss": 0.0159,
      "step": 45
    },
    {
      "epoch": 0.10660980810234541,
      "grad_norm": 9.90837574005127,
      "learning_rate": 4.466950959488273e-05,
      "loss": 0.0229,
      "step": 50
    },
    {
      "epoch": 0.11727078891257996,
      "grad_norm": 19.459095001220703,
      "learning_rate": 4.4136460554371006e-05,
      "loss": 0.0845,
      "step": 55
    },
    {
      "epoch": 0.1279317697228145,
      "grad_norm": 0.15913185477256775,
      "learning_rate": 4.360341151385928e-05,
      "loss": 0.0649,
      "step": 60
    },
    {
      "epoch": 0.13859275053304904,
      "grad_norm": 0.10663477331399918,
      "learning_rate": 4.307036247334755e-05,
      "loss": 0.0129,
      "step": 65
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.09200357645750046,
      "learning_rate": 4.253731343283582e-05,
      "loss": 0.0284,
      "step": 70
    },
    {
      "epoch": 0.15991471215351813,
      "grad_norm": 8.210641860961914,
      "learning_rate": 4.2004264392324094e-05,
      "loss": 0.0336,
      "step": 75
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.12569181621074677,
      "learning_rate": 4.147121535181237e-05,
      "loss": 0.0281,
      "step": 80
    },
    {
      "epoch": 0.1812366737739872,
      "grad_norm": 0.44192206859588623,
      "learning_rate": 4.093816631130064e-05,
      "loss": 0.0292,
      "step": 85
    },
    {
      "epoch": 0.19189765458422176,
      "grad_norm": 0.15402592718601227,
      "learning_rate": 4.0405117270788915e-05,
      "loss": 0.0495,
      "step": 90
    },
    {
      "epoch": 0.2025586353944563,
      "grad_norm": 17.383081436157227,
      "learning_rate": 3.987206823027719e-05,
      "loss": 0.0904,
      "step": 95
    },
    {
      "epoch": 0.21321961620469082,
      "grad_norm": 0.07923204451799393,
      "learning_rate": 3.9339019189765456e-05,
      "loss": 0.0503,
      "step": 100
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 0.07286439090967178,
      "learning_rate": 3.8805970149253736e-05,
      "loss": 0.0317,
      "step": 105
    },
    {
      "epoch": 0.2345415778251599,
      "grad_norm": 1.0418739318847656,
      "learning_rate": 3.8272921108742e-05,
      "loss": 0.0346,
      "step": 110
    },
    {
      "epoch": 0.24520255863539445,
      "grad_norm": 3.832359552383423,
      "learning_rate": 3.7739872068230284e-05,
      "loss": 0.0988,
      "step": 115
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.06542658805847168,
      "learning_rate": 3.720682302771855e-05,
      "loss": 0.0075,
      "step": 120
    },
    {
      "epoch": 0.26652452025586354,
      "grad_norm": 9.610258102416992,
      "learning_rate": 3.6673773987206824e-05,
      "loss": 0.0269,
      "step": 125
    },
    {
      "epoch": 0.2771855010660981,
      "grad_norm": 0.17276552319526672,
      "learning_rate": 3.61407249466951e-05,
      "loss": 0.0231,
      "step": 130
    },
    {
      "epoch": 0.2878464818763326,
      "grad_norm": 0.08185400068759918,
      "learning_rate": 3.560767590618337e-05,
      "loss": 0.0755,
      "step": 135
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.07418997585773468,
      "learning_rate": 3.5074626865671645e-05,
      "loss": 0.0424,
      "step": 140
    },
    {
      "epoch": 0.3091684434968017,
      "grad_norm": 2.326040267944336,
      "learning_rate": 3.454157782515991e-05,
      "loss": 0.1041,
      "step": 145
    },
    {
      "epoch": 0.31982942430703626,
      "grad_norm": 1.4266926050186157,
      "learning_rate": 3.400852878464819e-05,
      "loss": 0.0466,
      "step": 150
    },
    {
      "epoch": 0.3304904051172708,
      "grad_norm": 25.644779205322266,
      "learning_rate": 3.347547974413646e-05,
      "loss": 0.0492,
      "step": 155
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 4.534906387329102,
      "learning_rate": 3.294243070362473e-05,
      "loss": 0.033,
      "step": 160
    },
    {
      "epoch": 0.35181236673773986,
      "grad_norm": 10.8761625289917,
      "learning_rate": 3.240938166311301e-05,
      "loss": 0.0232,
      "step": 165
    },
    {
      "epoch": 0.3624733475479744,
      "grad_norm": 0.3756234645843506,
      "learning_rate": 3.187633262260128e-05,
      "loss": 0.0225,
      "step": 170
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 11.933363914489746,
      "learning_rate": 3.1343283582089554e-05,
      "loss": 0.0702,
      "step": 175
    },
    {
      "epoch": 0.3837953091684435,
      "grad_norm": 2.681648015975952,
      "learning_rate": 3.081023454157783e-05,
      "loss": 0.1197,
      "step": 180
    },
    {
      "epoch": 0.39445628997867804,
      "grad_norm": 0.5134532451629639,
      "learning_rate": 3.0277185501066102e-05,
      "loss": 0.0339,
      "step": 185
    },
    {
      "epoch": 0.4051172707889126,
      "grad_norm": 13.620699882507324,
      "learning_rate": 2.9744136460554372e-05,
      "loss": 0.0276,
      "step": 190
    },
    {
      "epoch": 0.4157782515991471,
      "grad_norm": 0.09190113842487335,
      "learning_rate": 2.9211087420042642e-05,
      "loss": 0.0086,
      "step": 195
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.10281543433666229,
      "learning_rate": 2.867803837953092e-05,
      "loss": 0.0129,
      "step": 200
    },
    {
      "epoch": 0.43710021321961623,
      "grad_norm": 6.414993762969971,
      "learning_rate": 2.814498933901919e-05,
      "loss": 0.0555,
      "step": 205
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 0.06216156855225563,
      "learning_rate": 2.7611940298507467e-05,
      "loss": 0.0076,
      "step": 210
    },
    {
      "epoch": 0.4584221748400853,
      "grad_norm": 12.08731746673584,
      "learning_rate": 2.7078891257995737e-05,
      "loss": 0.0403,
      "step": 215
    },
    {
      "epoch": 0.4690831556503198,
      "grad_norm": 0.10379679501056671,
      "learning_rate": 2.6545842217484007e-05,
      "loss": 0.0404,
      "step": 220
    },
    {
      "epoch": 0.47974413646055436,
      "grad_norm": 0.06435238569974899,
      "learning_rate": 2.6012793176972285e-05,
      "loss": 0.0072,
      "step": 225
    },
    {
      "epoch": 0.4904051172707889,
      "grad_norm": 0.07799974828958511,
      "learning_rate": 2.5479744136460555e-05,
      "loss": 0.0209,
      "step": 230
    },
    {
      "epoch": 0.5010660980810234,
      "grad_norm": 0.05462189391255379,
      "learning_rate": 2.494669509594883e-05,
      "loss": 0.006,
      "step": 235
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.0564899705350399,
      "learning_rate": 2.44136460554371e-05,
      "loss": 0.0277,
      "step": 240
    },
    {
      "epoch": 0.5223880597014925,
      "grad_norm": 0.6151730418205261,
      "learning_rate": 2.3880597014925373e-05,
      "loss": 0.0118,
      "step": 245
    },
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 3.0278522968292236,
      "learning_rate": 2.3347547974413646e-05,
      "loss": 0.0635,
      "step": 250
    },
    {
      "epoch": 0.5437100213219617,
      "grad_norm": 23.011789321899414,
      "learning_rate": 2.281449893390192e-05,
      "loss": 0.0231,
      "step": 255
    },
    {
      "epoch": 0.5543710021321961,
      "grad_norm": 2.13313889503479,
      "learning_rate": 2.2281449893390194e-05,
      "loss": 0.0391,
      "step": 260
    },
    {
      "epoch": 0.5650319829424307,
      "grad_norm": 0.14648886024951935,
      "learning_rate": 2.1748400852878467e-05,
      "loss": 0.0054,
      "step": 265
    },
    {
      "epoch": 0.5756929637526652,
      "grad_norm": 0.046188462525606155,
      "learning_rate": 2.1215351812366738e-05,
      "loss": 0.0069,
      "step": 270
    },
    {
      "epoch": 0.5863539445628998,
      "grad_norm": 0.047539375722408295,
      "learning_rate": 2.068230277185501e-05,
      "loss": 0.0067,
      "step": 275
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.051974523812532425,
      "learning_rate": 2.0149253731343285e-05,
      "loss": 0.0055,
      "step": 280
    },
    {
      "epoch": 0.6076759061833689,
      "grad_norm": 0.049149394035339355,
      "learning_rate": 1.961620469083156e-05,
      "loss": 0.0053,
      "step": 285
    },
    {
      "epoch": 0.6183368869936035,
      "grad_norm": 0.041319601237773895,
      "learning_rate": 1.9083155650319832e-05,
      "loss": 0.0221,
      "step": 290
    },
    {
      "epoch": 0.6289978678038379,
      "grad_norm": 0.05550704523921013,
      "learning_rate": 1.8550106609808106e-05,
      "loss": 0.0212,
      "step": 295
    },
    {
      "epoch": 0.6396588486140725,
      "grad_norm": 0.04463819041848183,
      "learning_rate": 1.8017057569296376e-05,
      "loss": 0.0348,
      "step": 300
    },
    {
      "epoch": 0.650319829424307,
      "grad_norm": 2.7232251167297363,
      "learning_rate": 1.7484008528784647e-05,
      "loss": 0.0339,
      "step": 305
    },
    {
      "epoch": 0.6609808102345416,
      "grad_norm": 0.04294276237487793,
      "learning_rate": 1.695095948827292e-05,
      "loss": 0.007,
      "step": 310
    },
    {
      "epoch": 0.6716417910447762,
      "grad_norm": 0.04751422628760338,
      "learning_rate": 1.6417910447761194e-05,
      "loss": 0.0058,
      "step": 315
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.06318726390600204,
      "learning_rate": 1.5884861407249468e-05,
      "loss": 0.0351,
      "step": 320
    },
    {
      "epoch": 0.6929637526652452,
      "grad_norm": 0.04593655467033386,
      "learning_rate": 1.535181236673774e-05,
      "loss": 0.0084,
      "step": 325
    },
    {
      "epoch": 0.7036247334754797,
      "grad_norm": 0.04337684437632561,
      "learning_rate": 1.4818763326226012e-05,
      "loss": 0.0048,
      "step": 330
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.3650192022323608,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.0054,
      "step": 335
    },
    {
      "epoch": 0.7249466950959488,
      "grad_norm": 0.04110950231552124,
      "learning_rate": 1.3752665245202559e-05,
      "loss": 0.0048,
      "step": 340
    },
    {
      "epoch": 0.7356076759061834,
      "grad_norm": 0.05691000819206238,
      "learning_rate": 1.3219616204690833e-05,
      "loss": 0.005,
      "step": 345
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 18.876996994018555,
      "learning_rate": 1.2686567164179105e-05,
      "loss": 0.031,
      "step": 350
    },
    {
      "epoch": 0.7569296375266524,
      "grad_norm": 0.8067087531089783,
      "learning_rate": 1.2153518123667377e-05,
      "loss": 0.0403,
      "step": 355
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 0.04626353457570076,
      "learning_rate": 1.162046908315565e-05,
      "loss": 0.0049,
      "step": 360
    },
    {
      "epoch": 0.7782515991471215,
      "grad_norm": 0.04179658740758896,
      "learning_rate": 1.1087420042643924e-05,
      "loss": 0.0047,
      "step": 365
    },
    {
      "epoch": 0.7889125799573561,
      "grad_norm": 0.05049879848957062,
      "learning_rate": 1.0554371002132196e-05,
      "loss": 0.0049,
      "step": 370
    },
    {
      "epoch": 0.7995735607675906,
      "grad_norm": 28.65748405456543,
      "learning_rate": 1.002132196162047e-05,
      "loss": 0.0207,
      "step": 375
    },
    {
      "epoch": 0.8102345415778252,
      "grad_norm": 0.05166960135102272,
      "learning_rate": 9.488272921108744e-06,
      "loss": 0.0268,
      "step": 380
    },
    {
      "epoch": 0.8208955223880597,
      "grad_norm": 0.03881421312689781,
      "learning_rate": 8.955223880597016e-06,
      "loss": 0.0206,
      "step": 385
    },
    {
      "epoch": 0.8315565031982942,
      "grad_norm": 0.0383550263941288,
      "learning_rate": 8.422174840085288e-06,
      "loss": 0.0043,
      "step": 390
    },
    {
      "epoch": 0.8422174840085288,
      "grad_norm": 0.04295238107442856,
      "learning_rate": 7.889125799573561e-06,
      "loss": 0.0042,
      "step": 395
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 1.7127622365951538,
      "learning_rate": 7.356076759061833e-06,
      "loss": 0.0053,
      "step": 400
    },
    {
      "epoch": 0.8635394456289979,
      "grad_norm": 0.049339987337589264,
      "learning_rate": 6.823027718550107e-06,
      "loss": 0.0044,
      "step": 405
    },
    {
      "epoch": 0.8742004264392325,
      "grad_norm": 0.06354337185621262,
      "learning_rate": 6.28997867803838e-06,
      "loss": 0.0045,
      "step": 410
    },
    {
      "epoch": 0.8848614072494669,
      "grad_norm": 0.1981351524591446,
      "learning_rate": 5.756929637526653e-06,
      "loss": 0.0054,
      "step": 415
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.03931286185979843,
      "learning_rate": 5.2238805970149255e-06,
      "loss": 0.0208,
      "step": 420
    },
    {
      "epoch": 0.906183368869936,
      "grad_norm": 0.0348835252225399,
      "learning_rate": 4.690831556503199e-06,
      "loss": 0.0157,
      "step": 425
    },
    {
      "epoch": 0.9168443496801706,
      "grad_norm": 0.03531981259584427,
      "learning_rate": 4.157782515991471e-06,
      "loss": 0.0063,
      "step": 430
    },
    {
      "epoch": 0.9275053304904051,
      "grad_norm": 4.256789684295654,
      "learning_rate": 3.624733475479744e-06,
      "loss": 0.0051,
      "step": 435
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 0.03756505623459816,
      "learning_rate": 3.0916844349680173e-06,
      "loss": 0.0045,
      "step": 440
    },
    {
      "epoch": 0.9488272921108742,
      "grad_norm": 0.16175320744514465,
      "learning_rate": 2.55863539445629e-06,
      "loss": 0.0075,
      "step": 445
    },
    {
      "epoch": 0.9594882729211087,
      "grad_norm": 0.03726266324520111,
      "learning_rate": 2.025586353944563e-06,
      "loss": 0.0041,
      "step": 450
    },
    {
      "epoch": 0.9701492537313433,
      "grad_norm": 19.503908157348633,
      "learning_rate": 1.4925373134328358e-06,
      "loss": 0.0224,
      "step": 455
    },
    {
      "epoch": 0.9808102345415778,
      "grad_norm": 0.04280271381139755,
      "learning_rate": 9.594882729211088e-07,
      "loss": 0.0602,
      "step": 460
    },
    {
      "epoch": 0.9914712153518124,
      "grad_norm": 0.03506707400083542,
      "learning_rate": 4.264392324093817e-07,
      "loss": 0.0233,
      "step": 465
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9381333333333334,
      "eval_loss": 0.27312836050987244,
      "eval_runtime": 18.3733,
      "eval_samples_per_second": 204.1,
      "eval_steps_per_second": 6.422,
      "step": 469
    },
    {
      "epoch": 1.0,
      "step": 469,
      "total_flos": 1.16237984421888e+18,
      "train_loss": 0.03354339535508964,
      "train_runtime": 172.9262,
      "train_samples_per_second": 86.742,
      "train_steps_per_second": 2.712
    }
  ],
  "logging_steps": 5,
  "max_steps": 469,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.16237984421888e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}